Related papers: EMMA-X: An EM-like Multilingual Pre-training Algor…
Controlling robots through natural language is pivotal for enhancing human-robot collaboration and synthesizing complex robot behaviors. Recent works that are trained on large robot datasets show impressive generalization abilities.…
Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using…
Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric training data leads to significant performance degradation in non-English languages. While existing…
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such representations: (1) alignment, which maps different independently…
Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In this paper, we first…
Meta learning with auxiliary languages has demonstrated promising improvements for cross-lingual natural language processing. However, previous studies sample the meta-training and meta-testing data from the same language, which limits the…
Sentence embedding models play a key role in various Natural Language Processing tasks, such as in Topic Modeling, Document Clustering and Recommendation Systems. However, these models rely heavily on parallel data, which can be scarce for…
Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers…
Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such…
Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…
Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation. This work addresses this limitation through a synthetic data…
Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching. Such requirements and assumptions are infeasible for most languages, especially for languages…
Extractive Reading Comprehension (ERC) has made tremendous advances enabled by the availability of large-scale high-quality ERC training data. Despite of such rapid progress and widespread application, the datasets in languages other than…
A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint…
Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this…
While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans. In this work, we propose a communication…
In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and…
Injecting external domain-specific knowledge (e.g., UMLS) into pretrained language models (LMs) advances their capability to handle specialised in-domain tasks such as biomedical entity linking (BEL). However, such abundant expert knowledge…
Recently, pre-training multilingual language models has shown great potential in learning multilingual representation, a crucial topic of natural language processing. Prior works generally use a single mixed attention (MA) module, following…
Word Representations form the core component for almost all advanced Natural Language Processing (NLP) applications such as text mining, question-answering, and text summarization, etc. Over the last two decades, immense research is…